Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/sdsrss/claudemd/claudemd-installgit clone --depth 1 https://github.com/sdsrss/claudemdWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/sdsrss/claudemd/claudemd-install)<a href="https://agentmods.dev/commands/sdsrss/claudemd/claudemd-install"><img src="https://agentmods.dev/badge/commands/sdsrss/claudemd/claudemd-install.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.00590 |
| Opus 5 | $0.00028 | $0.00295 |
| Sonnet 5 | $0.00011 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade B, and why
claudemd-install scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
This wraps `scripts/install.js` exactly the same way `SessionStart` does on the next session — copies `spec/CLAUDE*.md` + `OPERATOR.md` into `~/.claude/`, writes the hook manifest to `~/.claude/.claudemd-manifest.json`, What it actually says
Run: node ${CLAUDE_PLUGIN_ROOT}/scripts/install.js
This wraps scripts/install.js exactly the same way SessionStart does on the next session — copies spec/CLAUDE*.md + OPERATOR.md into ~/.claude/, writes the hook manifest to ~/.claude/.claudemd-manifest.json, and evicts any legacy claudemd hook entries from ~/.claude/settings.json. Idempotent — safe to re-run.
Backup is conditional, not universal: only genuine USER content is moved aside, into ~/.claude/backup-<ISO>/. An existing ~/.claude/CLAUDE.md that is already a claudemd spec is overwritten with no backup — that is the v0.23.11 data-loss fix, so the personal backup stays the sole entry in that namespace and CLAUDEMD_SPEC_ACTION=restore cannot return a spec instead of the user's own file. Pre-plugin hand-installed hook files go to their own handhook-backup-<ISO>/ namespace.
Surface the JSON output as a one-line human summary:
spec:fresh(no prior files) |backup-and-overwrite(existing files moved tobackup-<ISO>/).backupDir: path to the backup directory when applicable.userContentDetected: true— flag this loudly: the existing~/.claude/CLAUDE.mddid not look like a claudemd spec; the user's hand-written content is inbackupDir/CLAUDE.md. To bring it back on uninstall, runCLAUDEMD_SPEC_ACTION=restore /claudemd-uninstall.entries.length: number of registered hooks.cachePruned.removed: list of older cache version dirs reclaimed (best-effort; install succeeds regardless).
When to use: right after /plugin install claudemd@claudemd so hooks fire in THIS session. Claude Code does not honor postInstall, so without this command (or restarting the session) install.js runs on the next SessionStart and the current session sees /claudemd-status reporting plugin.hint == "cache-present-bootstrap-pending".
Not for routine upgrades — /claudemd-update is the right command for refreshing the spec into ~/.claude/ after a /plugin marketplace update + reinstall cycle; that command also diffs first and asks before overwriting.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +2 lines 7fa032cbe92d
- 5d ago First seen · 21 lines · 55 tokens per session scan B 8612ec2a7fbc
claudemd-install is a command published in the GitHub repository sdsrss/claudemd (2 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 590 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
brooks-health
Run a Brooks-Lint codebase health dashboard across all four dimensions.
brooks-debt
Run a Brooks-Lint tech debt assessment.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
audit
Onboard an existing codebase: every domain's checks over the whole tree, then a triaged plan to bring it in line.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.